| /external/tensorflow/tensorflow/contrib/tensor_forest/kernels/v4/ |
| stat_utils.h | 24 float GiniImpurity(const LeafStat& stats, int32 num_classes);
27 float WeightedGiniImpurity(const LeafStat& stats, int32 num_classes);
42 float SmoothedGini(float sum, float square, int num_classes);
45 float WeightedSmoothedGini(float sum, float square, int num_classes);
|
| stat_utils.cc | 24 // num_classes for smoothing each class, then Gini looks more like this:
33 float GiniImpurity(const LeafStat& stats, int32 num_classes) {
34 const float smoothed_sum = num_classes + stats.weight_sum();
36 2 * stats.weight_sum() + num_classes) /
40 float WeightedGiniImpurity(const LeafStat& stats, int32 num_classes) {
41 return stats.weight_sum() * GiniImpurity(stats, num_classes);
74 float SmoothedGini(float sum, float square, int num_classes) {
76 const float smoothed_sum = num_classes + sum;
77 return 1.0 - (square + 2 * sum + num_classes) / (smoothed_sum * smoothed_sum);
80 float WeightedSmoothedGini(float sum, float square, int num_classes) {
[all...] |
| /external/tensorflow/tensorflow/python/keras/_impl/keras/utils/ |
| np_utils_test.py | 30 num_classes = 5
32 expected_shapes = [(1, num_classes),
33 (3, num_classes),
34 (4, 3, num_classes),
35 (5, 4, 3, num_classes),
36 (3, num_classes)]
37 labels = [np.random.randint(0, num_classes, shape) for shape in shapes]
39 keras.utils.to_categorical(label, num_classes) for label in labels]
|
| np_utils.py | 25 def to_categorical(y, num_classes=None):
32 (integers from 0 to num_classes).
33 num_classes: total number of classes.
43 if not num_classes:
44 num_classes = np.max(y) + 1
46 categorical = np.zeros((n, num_classes))
48 output_shape = input_shape + (num_classes,)
|
| /external/tensorflow/tensorflow/contrib/metrics/python/ops/ |
| confusion_matrix_ops.py | 25 def confusion_matrix(labels, predictions, num_classes=None, dtype=dtypes.int32,
29 num_classes=num_classes, dtype=dtype, name=name,
|
| /external/tensorflow/tensorflow/contrib/tensor_forest/kernels/ |
| tree_utils_test.cc | 98 const int32 num_classes = 4; local
102 {num_accumulators, num_classes});
108 {num_accumulators, num_splits, num_classes});
116 const int32 num_classes = 4; local
121 {num_accumulators, num_classes});
127 {num_accumulators, num_splits, num_classes});
135 const int32 num_classes = 4; local
139 {num_accumulators, num_classes});
143 {num_accumulators, num_classes});
150 {num_accumulators, num_splits, num_classes});
169 const int32 num_classes = 4; local
[all...] |
| /external/robolectric-shadows/scripts/ |
| build-resources.rb | 20 num_classes = 0
24 x = START + INCR * num_classes
25 num_classes += 1
|
| /external/tensorflow/tensorflow/python/keras/_impl/keras/ |
| model_subclassing_test.py | 41 def __init__(self, use_bn=False, use_dp=False, num_classes=10):
45 self.num_classes = num_classes
48 self.dense2 = keras.layers.Dense(num_classes, activation='softmax')
65 def __init__(self, use_bn=False, use_dp=False, num_classes=(2, 3)):
69 self.num_classes = num_classes
72 self.dense2 = keras.layers.Dense(num_classes[0], activation='softmax')
73 self.dense3 = keras.layers.Dense(num_classes[1], activation='softmax')
94 def __init__(self, num_classes=2)
[all...] |
| /external/tensorflow/tensorflow/contrib/slim/python/slim/nets/ |
| inception_v3_test.py | 41 num_classes = 1000
44 logits, end_points = inception_v3.inception_v3(inputs, num_classes)
47 [batch_size, num_classes])
50 [batch_size, num_classes])
135 num_classes = 1000
138 _, end_points = inception_v3.inception_v3(inputs, num_classes)
142 [batch_size, num_classes])
146 [batch_size, num_classes])
159 num_classes = 1000
162 _, end_points = inception_v3.inception_v3(inputs, num_classes)
[all...] |
| inception_v2_test.py | 41 num_classes = 1000
44 logits, end_points = inception_v2.inception_v2(inputs, num_classes)
47 [batch_size, num_classes])
50 [batch_size, num_classes])
129 num_classes = 1000
132 _, end_points = inception_v2.inception_v2(inputs, num_classes)
140 inputs, num_classes, scope='depth_multiplied_net', depth_multiplier=0.5)
150 num_classes = 1000
153 _, end_points = inception_v2.inception_v2(inputs, num_classes)
161 inputs, num_classes, scope='depth_multiplied_net', depth_multiplier=2.0
[all...] |
| vgg_test.py | 36 num_classes = 1000
39 logits, _ = vgg.vgg_a(inputs, num_classes)
42 [batch_size, num_classes])
47 num_classes = 1000
50 logits, _ = vgg.vgg_a(inputs, num_classes, spatial_squeeze=False)
53 [batch_size, 2, 2, num_classes])
58 num_classes = 1000
62 _, end_points = vgg.vgg_a(inputs, num_classes, is_training=is_training)
75 num_classes = 1000
78 vgg.vgg_a(inputs, num_classes)
[all...] |
| inception_v1_test.py | 41 num_classes = 1000
44 logits, end_points = inception_v1.inception_v1(inputs, num_classes)
47 [batch_size, num_classes])
50 [batch_size, num_classes])
144 num_classes = 1000
149 logits, end_points = inception_v1.inception_v1(inputs, num_classes)
152 [batch_size, num_classes])
162 num_classes = 1000
165 logits, _ = inception_v1.inception_v1(inputs, num_classes)
167 self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
[all...] |
| alexnet_test.py | 35 num_classes = 1000
38 logits, _ = alexnet.alexnet_v2(inputs, num_classes)
41 [batch_size, num_classes])
46 num_classes = 1000
49 logits, _ = alexnet.alexnet_v2(inputs, num_classes, spatial_squeeze=False)
52 [batch_size, 4, 7, num_classes])
57 num_classes = 1000
60 _, end_points = alexnet.alexnet_v2(inputs, num_classes)
72 num_classes = 1000
75 alexnet.alexnet_v2(inputs, num_classes)
[all...] |
| overfeat_test.py | 35 num_classes = 1000
38 logits, _ = overfeat.overfeat(inputs, num_classes)
41 [batch_size, num_classes])
46 num_classes = 1000
49 logits, _ = overfeat.overfeat(inputs, num_classes, spatial_squeeze=False)
52 [batch_size, 2, 2, num_classes])
57 num_classes = 1000
60 _, end_points = overfeat.overfeat(inputs, num_classes)
72 num_classes = 1000
75 overfeat.overfeat(inputs, num_classes)
[all...] |
| resnet_v1.py | 130 num_classes=None,
164 num_classes: Number of predicted classes for classification tasks. If None
182 else both height_out and width_out equal one. If num_classes is None, then
184 average pooling. If num_classes is not None, net contains the pre-softmax
211 if num_classes is not None:
214 num_classes, [1, 1],
220 if num_classes is not None:
252 num_classes=None,
268 num_classes,
278 num_classes=None
[all...] |
| resnet_v2.py | 132 num_classes=None,
166 num_classes: Number of predicted classes for classification tasks. If None
186 else both height_out and width_out equal one. If num_classes is None, then
188 average pooling. If num_classes is not None, net contains the pre-softmax
225 if num_classes is not None:
228 num_classes, [1, 1],
234 if num_classes is not None:
265 num_classes=None,
281 num_classes,
291 num_classes=None
[all...] |
| /external/tensorflow/tensorflow/core/util/ctc/ |
| ctc_decoder.h | 42 CTCDecoder(int num_classes, int batch_size, bool merge_repeated)
43 : num_classes_(num_classes),
44 blank_index_(num_classes - 1),
60 int num_classes() { return num_classes_; } function in class:tensorflow::ctc::CTCDecoder
73 CTCGreedyDecoder(int num_classes, int batch_size, bool merge_repeated)
74 : CTCDecoder(num_classes, batch_size, merge_repeated) {}
|
| ctc_loss_calculator.h | 94 int num_classes, const Vector& seq_len,
123 auto num_classes = inputs[0].cols(); local
136 if (inputs[t].cols() != num_classes) {
138 " to be: ", num_classes,
161 batch_size, num_classes, seq_len, labels, &max_u_prime, &l_primes);
167 auto ComputeLossAndGradients = [this, num_classes, &labels, &l_primes,
196 Matrix y(num_classes, seq_len(b));
206 // y, prob are in num_classes x seq_len(b)
262 max_seq_len * num_classes *
264 max_seq_len * 2 * (2 * num_classes + 1)
[all...] |
| /external/tensorflow/tensorflow/core/kernels/ |
| multinomial_op_gpu.cu.cc | 41 __global__ void MultinomialKernel(int32 nthreads, const int32 num_classes,
45 const int maxima_idx = index / num_classes;
49 static_cast<UnsignedOutputType>(index % num_classes));
61 int num_classes, int num_samples,
74 bsc.set(2, num_classes);
78 boc.set(2, num_classes);
84 Eigen::array<int, 3> bsc{batch_size, num_samples, num_classes};
85 Eigen::array<int, 3> boc{batch_size, 1, num_classes};
106 const int32 work_items = batch_size * num_samples * num_classes;
109 d.stream()>>>(config.virtual_thread_count, num_classes,
[all...] |
| multinomial_op.cc | 50 int num_classes, int num_samples,
62 int num_classes, int num_samples,
71 auto DoWork = [ctx, num_samples, num_classes, &gen, &output, &logits](
84 ctx->allocate_temp(DT_DOUBLE, TensorShape({num_classes}),
92 for (int64 j = 0; j < num_classes; ++j) {
104 for (int64 j = 0; j < num_classes; ++j) {
112 const double* cdf_end = cdf.data() + num_classes;
122 50 * (num_samples * std::log(num_classes) / std::log(2) + num_classes);
163 const int num_classes = static_cast<int>(logits_t.dim_size(1)) variable
[all...] |
| xent_op_test.cc | 24 static Graph* Xent(int batch_size, int num_classes) {
26 Tensor logits(DT_FLOAT, TensorShape({batch_size, num_classes}));
28 Tensor labels(DT_FLOAT, TensorShape({batch_size, num_classes}));
|
| /external/tensorflow/tensorflow/contrib/nn/python/ops/ |
| sampling_ops.py | 116 num_classes,
175 weights: A `Tensor` or `PartitionedVariable` of shape `[num_classes, dim]`,
177 has shape [num_classes, dim]. The (possibly-sharded) class embeddings.
178 biases: A `Tensor` or `PartitionedVariable` of shape `[num_classes]`.
189 num_classes: An `int`. The number of possible classes.
209 if num_sampled > num_classes:
210 raise ValueError("num_sampled ({}) cannot be greater than num_classes ({})".
211 format(num_sampled, num_classes))
227 range_max=num_classes)
239 num_classes=num_classes
[all...] |
| /external/tensorflow/tensorflow/contrib/tensor_forest/python/ |
| tensor_forest_test.py | 32 num_classes=2,
37 self.assertEquals(2, hparams.num_classes)
46 num_classes=2,
55 num_classes=2,
69 num_classes=4,
85 num_classes=4,
101 num_classes=4,
121 num_classes=4,
144 num_classes=4,
|
| /external/opencv/ml/src/ |
| mltestset.cpp | 63 int num_classes, ... )
93 if( num_classes < 1 )
94 CV_ERROR( CV_StsBadArg, "num_classes parameter must be positive" );
133 num_classes = MIN( num_samples, num_classes );
141 last_idx = num_samples * (cur_class + 1) / num_classes - 1;
|
| /external/tensorflow/tensorflow/contrib/boosted_trees/estimator_batch/ |
| estimator.py | 76 num_classes=n_classes)
85 if learner_config.num_classes == 0:
86 learner_config.num_classes = n_classes
87 elif learner_config.num_classes != n_classes:
89 (learner_config.num_classes, n_classes))
154 learner_config.num_classes = 2
156 learner_config.num_classes = label_dimension
|
